feat(eventstore): exclude aggregate IDs when event_type occurred (#8940)

# Which Problems Are Solved

For truly event-based notification handler, we need to be able to filter
out events of aggregates which are already handled. For example when an
event like `notify.success` or `notify.failed` was created on an
aggregate, we no longer require events from that aggregate ID.

# How the Problems Are Solved

Extend the query builder to use a `NOT IN` clause which excludes
aggregate IDs when they have certain events for a certain aggregate
type. For optimization and proper index usages, certain filters are
inherited from the parent query, such as:

- Instance ID
- Instance IDs
- Position offset

This is a prettified query as used by the unit tests:

```sql
SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision
FROM eventstore.events2
WHERE instance_id = $1
    AND aggregate_type = $2 
    AND event_type = $3
    AND "position" > $4
    AND aggregate_id NOT IN (
        SELECT aggregate_id
        FROM eventstore.events2
        WHERE aggregate_type = $5
        AND event_type = ANY($6)
        AND instance_id = $7
        AND "position" > $8
    )
ORDER BY "position" DESC, in_tx_order DESC
LIMIT $9
```

I used this query to run it against the `oidc_session` aggregate looking
for added events, excluding aggregates where a token was revoked,
against a recent position. It fully used index scans:

<details>

```json
[
  {
    "Plan": {
      "Node Type": "Index Scan",
      "Parallel Aware": false,
      "Async Capable": false,
      "Scan Direction": "Forward",
      "Index Name": "es_projection",
      "Relation Name": "events2",
      "Alias": "events2",
      "Actual Rows": 2,
      "Actual Loops": 1,
      "Index Cond": "((instance_id = '286399006995644420'::text) AND (aggregate_type = 'oidc_session'::text) AND (event_type = 'oidc_session.added'::text) AND (\"position\" > 1731582100.784168))",
      "Rows Removed by Index Recheck": 0,
      "Filter": "(NOT (hashed SubPlan 1))",
      "Rows Removed by Filter": 1,
      "Plans": [
        {
          "Node Type": "Index Scan",
          "Parent Relationship": "SubPlan",
          "Subplan Name": "SubPlan 1",
          "Parallel Aware": false,
          "Async Capable": false,
          "Scan Direction": "Forward",
          "Index Name": "es_projection",
          "Relation Name": "events2",
          "Alias": "events2_1",
          "Actual Rows": 1,
          "Actual Loops": 1,
          "Index Cond": "((instance_id = '286399006995644420'::text) AND (aggregate_type = 'oidc_session'::text) AND (event_type = 'oidc_session.access_token.revoked'::text) AND (\"position\" > 1731582100.784168))",
          "Rows Removed by Index Recheck": 0
        }
      ]
    },
    "Triggers": [
    ]
  }
]
```

</details>

# Additional Changes

- None

# Additional Context

- Related to https://github.com/zitadel/zitadel/issues/8931

---------

Co-authored-by: adlerhurst <silvan.reusser@gmail.com>
This commit is contained in:
Tim Möhlmann
2024-11-25 17:25:11 +02:00
committed by GitHub
parent 91290d6195
commit ff70ede7c7
5 changed files with 216 additions and 10 deletions

View File

@@ -21,6 +21,7 @@ type SearchQueryBuilder struct {
instanceIDs []string
editorUser string
queries []*SearchQuery
excludeAggregateIDs *ExclusionQuery
tx *sql.Tx
lockRows bool
lockOption LockOption
@@ -68,6 +69,10 @@ func (b *SearchQueryBuilder) GetQueries() []*SearchQuery {
return b.queries
}
func (b *SearchQueryBuilder) GetExcludeAggregateIDs() *ExclusionQuery {
return b.excludeAggregateIDs
}
func (b *SearchQueryBuilder) GetTx() *sql.Tx {
return b.tx
}
@@ -136,6 +141,20 @@ func (q SearchQuery) GetPositionAfter() float64 {
return q.positionAfter
}
type ExclusionQuery struct {
builder *SearchQueryBuilder
aggregateTypes []AggregateType
eventTypes []EventType
}
func (q ExclusionQuery) GetAggregateTypes() []AggregateType {
return q.aggregateTypes
}
func (q ExclusionQuery) GetEventTypes() []EventType {
return q.eventTypes
}
// Columns defines which fields of the event are needed for the query
type Columns int8
@@ -346,6 +365,16 @@ func (builder *SearchQueryBuilder) AddQuery() *SearchQuery {
return query
}
// ExcludeAggregateIDs excludes events from the aggregate IDs returned by the [ExclusionQuery].
// There can be only 1 exclusion query. Subsequent calls overwrite previous definitions.
func (builder *SearchQueryBuilder) ExcludeAggregateIDs() *ExclusionQuery {
query := &ExclusionQuery{
builder: builder,
}
builder.excludeAggregateIDs = query
return query
}
// Or creates a new sub query on the search query builder
func (query SearchQuery) Or() *SearchQuery {
return query.builder.AddQuery()
@@ -398,3 +427,20 @@ func (query *SearchQuery) matches(command Command) bool {
}
return true
}
// AggregateTypes filters for events with the given aggregate types
func (query *ExclusionQuery) AggregateTypes(types ...AggregateType) *ExclusionQuery {
query.aggregateTypes = types
return query
}
// EventTypes filters for events with the given event types
func (query *ExclusionQuery) EventTypes(types ...EventType) *ExclusionQuery {
query.eventTypes = types
return query
}
// Builder returns the SearchQueryBuilder of the sub query
func (query *ExclusionQuery) Builder() *SearchQueryBuilder {
return query.builder
}